Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuine behavioral context beyond that: grouping of identical failures by error fingerprint for runs/workflows, a focused evidence-based diagnosis for jobs/attempts, and an explicit empty result when no failure evidence exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four compact sentences, each load-bearing: purpose, per-target behavior, empty-result caveat, and the recommended-call cue. The primary guidance is front-loaded and the API path trailer is minimal overhead.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so reasonably: grouping, evidence, and empty results are all mentioned. It stops short of describing the diagnosis structure (fields, evidence shape), so an agent knows what it will get conceptually but not its form.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description earns above-baseline credit by explaining how each target_type value changes the response semantics (grouped vs focused diagnosis). It still does not clarify format expectations for target_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (get) and resource (failure diagnosis) and enumerates the four accepted targets (run, workflow, job, attempt), which no sibling covers. It also distinguishes itself from log/status siblings by describing grouped-by-fingerprint vs focused diagnosis output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly positions itself as 'The best first call when a run failed,' giving clear entry-point guidance. It does not, however, name alternatives (e.g. depot_ci_get_job_logs or depot_ci_get_run_status) or state when to skip it, so routing is only partially resolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.